English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Graph Neural Networks (GNNs) excel in various domains, from detectinge-commerce spam to social network classification problems. However, the lack ofpublic graph datasets hampers research progress, particularly in heterogeneousinformation networks (HIN). The demand for datasets for fair HIN comparisons isgrowing due to advancements in GNN interpretation models. In response, wepropose SynHIN, a unique method for generating synthetic heterogeneousinformation networks. SynHIN identifies motifs in real-world datasets,summarizes graph statistics, and constructs a synthetic network. Our approachutilizes In-Cluster and Out-Cluster Merge modules to build the synthetic HINfrom primary motif clusters. After In/Our-Cluster mergers and a post-pruningprocess fitting the real dataset constraints, we ensure the synthetic graphstatistics align closely with the reference one. SynHIN generates a syntheticheterogeneous graph dataset for node classification tasks, using the primarymotif as the explanation ground truth. It can adapt and address the lack ofheterogeneous graph datasets and motif ground truths, proving beneficial forassessing heterogeneous graph neural network explainers. We further present abenchmark dataset for future heterogeneous graph explainer model research. Ourwork marks a significant step towards explainable AI in HGNNs.

SynHIN: Generating Synthetic Heterogeneous Information Network for Explainable AI